Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific conditions or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iamine
    0.41
     Romana
    0.41
    PA
    0.40
    फेक्ट
    0.40
     पंक्ति
    0.39
    IT
    0.39
     इत
    0.39
     Worksheet
    0.38
     Feminist
    0.38
    PL
    0.38
    POSITIVE LOGITS
     leicht
    0.46
     vapors
    0.42
     neun
    0.42
     legger
    0.41
     thermocou
    0.41
     Ecco
    0.41
    چه
    0.41
     crackers
    0.41
     thermost
    0.41
     succulents
    0.40
    Act Density 0.001%

    No Known Activations